download data and pre-process

# Download the file
path_to_zip = tf.keras.utils.get_file(
    'spa-eng.zip', origin='http://storage.googleapis.com/download.tensorflow.org/data/spa-eng.zip',
    extract=True)

path_to_file = os.path.dirname(path_to_zip)+"/spa-eng/spa.txt"

# Converts the unicode file to ascii
def unicode_to_ascii(s):
  return ''.join(c for c in unicodedata.normalize('NFD', s)
      if unicodedata.category(c) != 'Mn')


def preprocess_sentence(w):
  w = unicode_to_ascii(w.lower().strip())

  # creating a space between a word and the punctuation following it
  # eg: "he is a boy." => "he is a boy ."
  # Reference:- https://stackoverflow.com/questions/3645931/python-padding-punctuation-with-white-spaces-keeping-punctuation
  w = re.sub(r"([?.!,¿])", r" \1 ", w)
  w = re.sub(r'[" "]+', " ", w)

  # replacing everything with space except (a-z, A-Z, ".", "?", "!", ",")
  w = re.sub(r"[^a-zA-Z?.!,¿]+", " ", w)

  w = w.strip()

  # adding a start and an end token to the sentence
  # so that the model know when to start and stop predicting.
  w = '<start> ' + w + ' <end>'
  return w
  
 def create_dataset(path, num_examples):
  lines = io.open(path, encoding='UTF-8').read().strip().split('\n')

  word_pairs = [[preprocess_sentence(w) for w in l.split('\t')]  for l in lines[:num_examples]]

  return zip(*word_pairs)